Papers with Code 아카이브

Question Answering

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 19
평가표: 153
보존된 평가 기록: 1,781

Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.

( Image credit: SQuAD )

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/stanfordnlp/dspy

공식 코드

DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

https://github.com/stanfordnlp/mac-network

공식 코드

GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering

https://github.com/stanfordnlp/mixed-distribution-retrieval

공식 코드

Resources and Evaluations for Multi-Distribution Dense Information Retrieval

https://github.com/stanlei52/aqvsr

공식 코드

AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant

https://github.com/stanlei52/tqvsr

공식 코드

AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant

https://github.com/staoxiao/retromae

공식 코드

RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder

https://github.com/stardust-coder/japanese-lm-med-harness

공식 코드

Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources

https://github.com/stareru/csqa_debertav3

공식 코드

Solution of DeBERTaV3 on CommonsenseQA

https://github.com/starriver030515/synthvlm

공식 코드

SynthVLM: High-Efficiency and High-Quality Synthetic Data for Vision Language Models

https://github.com/starscream-11813/variational-mathematical-reasoning

공식 코드

Math Word Problem Solving by Generating Linguistic Variants of Problem Statements

https://github.com/starsuzi/adaptive-rag

공식 코드

Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity

https://github.com/starsuzi/as-convqa

공식 코드

Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement

https://github.com/starsuzi/pro-convqa

공식 코드

Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning

https://github.com/starsuzi/t-sas

공식 코드

Test-Time Self-Adaptive Small Language Models for Question Answering

https://github.com/stasl0217/UKGE

공식 코드

Embedding Uncertain Knowledge Graphs

https://github.com/stellali7/mediq

공식 코드

MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning

https://github.com/stellalisy/mediq

공식 코드

MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning

https://github.com/stephanlorenzen/majorityvotebounds

공식 코드

Split-kl and PAC-Bayes-split-kl Inequalities for Ternary Random Variables

https://github.com/stevezhangza/nash-chain-of-thought

공식 코드

Nash CoT: Multi-Path Inference with Preference Equilibrium

https://github.com/stogiannidis/srbench

공식 코드

Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models

https://github.com/stonybrooknlp/dire

공식 코드

Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning

https://github.com/stonybrooknlp/ircot

공식 코드

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions

https://github.com/stonybrooknlp/musique

공식 코드

MuSiQue: Multihop Questions via Single-hop Question Composition

https://github.com/stonybrooknlp/teabreac

공식 코드

Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts

https://github.com/sts-vlcc/sts-vlcc

공식 코드

Listen Then See: Video Alignment with Speaker Attention

https://github.com/studio-ousia/bpr

공식 코드

Efficient Passage Retrieval with Hashing for Open-domain Question Answering

https://github.com/studio-ousia/luke

공식 코드

LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention

https://github.com/studio-ousia/ntee

공식 코드

Learning Distributed Representations of Texts and Entities from Knowledge Base

https://github.com/stwisdom/urnn

공식 코드

Full-Capacity Unitary Recurrent Neural Networks

https://github.com/subho406/OmniNet

공식 코드

OmniNet: A unified architecture for multi-modal multi-task learning

https://github.com/sufianj/def_extraction

공식 코드

Extracting Definienda in Mathematical Scholarly Articles with Transformers

https://github.com/suletekkesinoglu/xai_llm_rag

공식 코드

From Feature Importance to Natural Language Explanations Using LLMs with RAG

https://github.com/sunanhe/meddr

공식 코드

GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration

https://github.com/sungyeonparkk/nuplanqa

공식 코드

NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models

https://github.com/sunlab-osu/CliniQG4QA

공식 코드

CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering

https://github.com/sunlab-osu/reasonbert

공식 코드

ReasonBERT: Pre-trained to Reason with Distant Supervision

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.